We design the function which describe the attribute probability of the stroke segment. We also define the contributive value of the grid and propose the concept of the expanded grid, and we got good results of Cross Recognition.
我们用网格化特征记录了汉字的结构信息,设计了定义笔段方向隶属度函数、网格的贡献度及扩充网格的概念,有效的反映了汉字的信息。
参考来源 - 基于实虚笔段方向特征粗分方法的联机手写汉字识别The paper describes basic process of computer character recognition system, gives some common-used Chinese character recognition methods, The main improvements to available character recognition methods are:1、A novel method of stroke extraction is proposed.
论文在总结学术上已有关于计算机文字识别成果的基础上,描述了计算机文字识别的基本过程,介绍了几种常用的汉字字符识别方法,对已有字符识别方法的改进主要有:(一)提出了一种提取汉字笔段的新方法。
参考来源 - 字符识别中笔段及特征提取方法的研究·2,447,543篇论文数据,部分数据来源于NoteExpress
最后该文给出了印刷体和手写体汉字笔段提取的实验结果。
Experimental results for several fonts of printed Chinese characters and handwritten Chinese characters show that the proposed method is effective and robust.
基于笔段的笔迹重构方法中,笔迹重构实质上就是笔段的排序问题。
A stroke segment-based algorithm was proposed, which is equal to the problem of ordering the stroke segments in nature.
该方法借鉴笔段链码特征,建立以笔画一笔段数目作为检索参数的字典库;
This method build a dictionary library that take the strokes and stroke segment as the index parameters by making use of the stroke segment and chain code character;
应用推荐